All nine kinds in one list: what an agent loads, what it runs, what it
reads and what bundles the rest. 412,032 of
them, each with its token cost per session, a security scan with the
line that triggered it, and whether it is the original or one of the
copies.
Research, create, improve, migrate, evaluate, package, install-check, govern, and safely publish qiaomu-flavored agent skills from workflows, prompts, transcripts, docs, SOPs, runbooks, scripts, or notes. Use for new or existing skills, prior-art synthesis, routing/trigger boundaries, trigger or output evals, Skill…
MCP server for interacting with EVM-compatible blockchains - supports 22 tools and 10 prompts across 60+ networks. Runs locally from the @mcpdotdirect/evm-mcp-server npm package.
★not rated 379▲
+1 yesterdayA
tokens not measured
originalMIT
Path traversal attacks occur when user-controlled input is used to construct file paths, allowing attackers to access files outside the intended directory. This can lead to unauthorized file access, data leakage, or system compromise.
A tool for retrieving the full text and comments of a linux.do forum post, including which comments reply to others. It uses the browser's logged-in session and can return threaded or fallback comment data.
Build a portable knowledge base of your video (and eventually photo) archive across multiple SSDs or directly from an Apple Photos library. For each clip: GPS + reverse-geocoded place, speaker-diarized multi-lingual transcript with English translation, face detection + embeddings for later named-person queries…
Helps a coding agent build LINE bots / clients with the @evex/linejs library — JSR package, Deno-first, runs on Node/Bun too. Use when the user asks to write LINE bots, automate LINE accounts, work with LINE Thrift APIs, or wrap the AI "Agent I" feature.
A workflow for tracking Facebook posts associated with the Ba Nini counter-indicator and analysing them in Chinese. A counter-indicator treats a person or group’s public views as signals that may point in the opposite direction.
This skill helps you build LLM-powered applications with Claude. Choose the right surface based on your needs, detect the project language, then read the relevant language-specific documentation.
Use when working with MobileClaw's phone-to-desktop Codex bridge, including bridge setup, Tailscale access, MobileClaw-originated tasks, and safe desktop configuration.
Creates Python projects with proper structure, virtual environments, and dependency management. Use when users request to create a new Python project, set up a Python development environment, or initialize a Python application with standard tooling.
This skill should be used when taking a single software feature from intent to shipped as a solo developer — goal-first, TDD, deterministic verification, evidence only where it earns its keep, and human judgment at the two moments that matter (goal approval, merge). Trigger when the user says "let's build feature X"…
Multi-agent task orchestration with visual terminal panes. Decomposes complex dev tasks into parallel Claude Code instances coordinated through dependency-aware waves.
A tool that turns a travel plan into a single HTML page designed for phones and offline reading. The page can include an interactive map, a daily timeline, and reminders to book things before departure.
Use UModel from your agent: read entities, relationships, topology, and the model itself; discover and follow entity-linked RunbookSet Skills; and run model-guided root-cause analysis. Bundles three UModel skills.
Analyze errors and bugs, identify root causes, and provide systematic fix recommendations.
★not rated 375▲
+1 6mo agoA18 tokens
originalMIT
At most 3 mods per repository are shown here, and a mod shipped inside a plugin is left to that plugin's page — the rest are on their repository pages: